{
  "device": "cuda",
  "math_check": {
    "distance_table": [
      [
        0.0,
        1.0,
        2.0,
        3.0,
        4.0,
        5.0,
        6.0,
        7.0,
        8.0
      ],
      [
        8.0,
        7.0,
        6.0,
        5.0,
        4.0,
        3.0,
        2.0,
        1.0,
        0.0
      ]
    ],
    "shortest_path_assertions": [
      true,
      true
    ],
    "greedy_progress_violations": 0,
    "ideal_progress_hinge_sum": 0.0,
    "math_pass": true
  },
  "baseline_runs": [
    {
      "train_reward_last40": 0.675,
      "eval_success": 0.5,
      "eval_steps_success_only": 4.0,
      "critic_loss_last40": 0.07858757711946965,
      "distance_abs_error_last40": null
    },
    {
      "train_reward_last40": 0.75,
      "eval_success": 0.5,
      "eval_steps_success_only": 4.0,
      "critic_loss_last40": 0.06681055419612676,
      "distance_abs_error_last40": null
    }
  ],
  "idea_runs": [
    {
      "train_reward_last40": 0.775,
      "eval_success": 0.5,
      "eval_steps_success_only": 4.0,
      "critic_loss_last40": 0.07392901862040162,
      "distance_abs_error_last40": 2.983294904232025
    },
    {
      "train_reward_last40": 0.725,
      "eval_success": 0.5,
      "eval_steps_success_only": 4.0,
      "critic_loss_last40": 0.0675667256815359,
      "distance_abs_error_last40": 2.5086710512638093
    }
  ],
  "baseline": {
    "train_reward_last40": 0.7125,
    "eval_success": 0.5,
    "eval_steps_success_only": 4.0,
    "critic_loss_last40": 0.07269906565779821
  },
  "idea": {
    "train_reward_last40": 0.75,
    "eval_success": 0.5,
    "eval_steps_success_only": 4.0,
    "critic_loss_last40": 0.07074787215096875,
    "distance_abs_error_last40": 2.745982977747917
  }
}